Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    structured mathematical expressions or alignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    aligned $$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    انيف
    -0.58
     Swann
    -0.57
    -0.56
     Uribe
    -0.55
    ACON
    -0.55
     Sheppard
    -0.53
    khov
    -0.53
     oeufs
    -0.52
     Hooper
    -0.52
     Cordero
    -0.52
    POSITIVE LOGITS
    InputBorder
    0.85
    aligned
    0.82
    PerformLayout
    0.73
    ActionPerformed
    0.73
    存于互联网档案馆
    0.71
    endphp
    0.69
    \{\\
    0.68
    SharedCtor
    0.68
     transfieras
    0.68
    ContentAsync
    0.64
    Act Density 0.022%

    No Known Activations